Agent Vision Toolkit skill for Codex

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

How to install Agent Vision Toolkit in Codex

In Codex, ask the built-in skill installer for it:

Type this in Codex: $skill-installer is the skill installer built into Codex, and it downloads the skill from GitHub. Restart Codex if the skill doesn't show up. Check the repo README for any setup the skill needs. Source: Codex skills docs.

Or copy the skill folder (the one with SKILL.md) into ~/.agents/skills to use it in every project, or into .agents/skills in a repo to share it with that repo. Codex picks up new skills automatically. (where Codex loads skills)

What it contains

About this listing

Agent Vision Toolkit is a community collection of agent skills on GitHub by Anionex: folders with a SKILL.md file, the format Codex loads skills from. Its README mentions Codex. It passed the CodexStacks quality filter for skills (at least 100 stars, pushed in the last 90 days, not a fork or a list, and at least one SKILL.md with a name and description). OpenAI hasn't reviewed it, but it passed our Codex install check on Oct 25, 2026 (an install and load check, not a code review). From its files we found 1 skill. It's one of 137 listings in the Creativity category (category assigned by CodexStacks from the repo's topics and description). It also appears in best Codex plugins for design and UI.

Agent Vision Toolkit FAQ

Details

Type

Skill

Category

Creativity (assigned by us)

Source

Community

Author

Anionex

License

MIT

GitHub stars

1,251 (at last sync)

Last push

2026-10-13

GitHub topics

agent, claude-code, computer-use, deepseek, dsh-plugin, glm, harness-engineering, multimodal, opencode, text-only-llm, vision, vision-language-model

Source

https://github.com/Anionex/agent-vision-toolkit

Website

https://agent-vision.anionex.me

Listed via

GitHub search: Codex skills (SKILL.md)

Install check by CodexStacks

Passed on Oct 25, 2026 with Codex CLI 0.163.0: Codex loaded its skills. proof · how we check

Something wrong or missing? Submit or improve this listing. Listings also refresh automatically every night.

For maintainers: badge and embeds

Maintain Agent Vision Toolkit? Add the badge; it links to this page.

Markdown

HTML

Embed card (static HTML and inline CSS, no JavaScript). Preview:

Markdown summary

More on badges, embeds and keeping your listing up to date: CodexStacks for plugin authors.

Also in Creativity

UI UX Pro Max Skill

An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.

CommunitySkillCreativity

Taste Skill

tasteskill v2: art direction for websites, product pages, dashboards and app screens, checked in a real browser.

CommunityPluginCreativity

Archify

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

CommunitySkillCreativity

Diagram Design

Architecture, architecture delta, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar, loop, nested, tree, org chart, layer stack, exploded/plan, Venn…

CommunityPluginCreativity

Hallmark

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

CommunitySkillCreativity

Text To Cad

The text-to-cad plugin gives your agent local workflows for generating 3D models as STEP, GLB, STL or 3MF files. It also does design for manufacturing checks, generates engineering drawings, and connects to popular 3D…

CommunityPluginCreativity

All 137 creativity listings →